Clinical Report: Radiomic Assessment of Biplanar Ultrasound Imaging

Overview

This study evaluates the effectiveness of radiomics models using biplanar ultrasound imaging to differentiate non-mass breast carcinoma (NMBC) from mastitis. The findings indicate that while the fusion model showed superior performance in the training cohort, its generalizability was limited in the validation cohort.

Background

Non-mass breast carcinoma (NMBC) poses a significant diagnostic challenge due to overlapping sonographic features with mastitis, which can lead to misdiagnosis and delayed treatment. Accurate differentiation is crucial as NMBC requires prompt oncological management, unlike mastitis, which typically warrants conservative therapy.

Data Highlights

Key Findings

• The fusion model outperformed single-plane models in the training cohort (AUC = 94.2%, accuracy = 87.6%).
• In the validation cohort, the performance of the transverse, longitudinal, and fusion models was comparable (AUC = 0.730, 0.823, and 0.800, respectively; accuracy = 69.0%, 78.6%, and 78.6%, respectively).
• The combined clinical-radiomics model showed performance metrics of AUC: 0.861–0.884 in the validation cohort.
• Likelihood ratio tests confirmed that radiomics features and clinical variables contributed independently to the prediction.
• Calibration and decision curve analysis indicated limited generalizability of the fusion model in the validation cohort.

Clinical Implications

The study suggests that integrating clinical variables with radiomics features may enhance diagnostic accuracy for distinguishing NMBC from mastitis. Clinicians should consider employing combined clinical-radiomics models for improved decision-making in preoperative assessments.

Conclusion

Biplanar ultrasound imaging-based radiomics models show potential for differentiating NMBC from mastitis, although their generalizability requires further validation.

Related Resources & Content

1. Frontiers in Oncology, 2026 -- Multimodal feature fusion model for breast mass malignant risk stratification
2. Frontiers in Oncology, 2026 -- Diagnostic value of multimodal ultrasound imaging in triple-negative breast cancer
3. Frontiers in Endocrinology, 2026 -- A multimodal ultrasound-based model combining tumor radiomics and axillary lymph node morphologic classification for predicting axillary nodal burden in breast cancer
4. Frontiers in Oncology, 2026 -- Ultrasound-based radiomics and habitat analysis for noninvasive assessment of Ki-67 overexpression in breast cancer
5. Nonmass Lesions on Breast Ultrasound: Radiologic-Pathologic Correlation and a Practical Guide to Diagnostic Approach - PMC
6. ACR Appropriateness Criteria® Breast Imaging During Pregnancy - ScienceDirect
7. The value of intratumoral and peritumoral ultrasound radiomics model constructed using multiple machine learning algorithms for non-mass breast cancer | Scientific Reports
8. Nonmass Lesions on Breast Ultrasound: Radiologic-Pathologic Correlation and a Practical Guide to Diagnostic Approach - PMC
9. ACR Appropriateness Criteria® Breast Imaging During Pregnancy - ScienceDirect
10. The value of intratumoral and peritumoral ultrasound radiomics model constructed using multiple machine learning algorithms for non-mass breast cancer | Scientific Reports